Machine Learning and Convolutional Neural Networks to Replace Manual Qubit Characterization Methods?

Excerpt below is from the University of Melbourne.  Entire piece is worth the read.  See below for links.  Here, we showcase the section on quantum computing and machine learning.  Because quantum is coming.  Qubit.  

Machine learning to scale up the quantum computer

MACHINE LEARNING

Machine learning is an emerging area of research which is revolutionizing almost every field of research, from medical science to image processing, robotics, and material design.

A carefully trained machine learning algorithm can process very large data sets with enormous efficiency.

One branch of machine learning is known as convolutional neural network (CNN) – an extremely powerful tool for image recognition and classification problems. When a CNN is trained on thousands of sample images, it can precisely recognize unknown images (including noise) and perform classifications.

Recognising that the principle underpinning the established spatial metrology of qubit atoms is basically recognising and classifying feature maps of STM images, we decided to train a CNN on the computed STM images. The work is published in the NPJ Computational Materials journal.

Computed scanning tunneling microscope (STM) images of phosphorus atoms qubits in silicon used to train a convolutional neural network (CNN), capable of autonomous and high-throughput qubit characterization with an exact atom precision in both, their spatial locations and atom count. Image: M.Usman/ University of Melbourne

 

The training involved 100,000 STM images and achieved a remarkable learning of above 99 per cent for the CNN. We then tested the trained CNN for 17600 test images including blurring and asymmetry noise typically present in the realistic environments.

The CNN classified the test images with an accuracy of above 98 per cent, confirming that this machine learning-based technique could process qubit measurement data with high-throughput, high precision, and minimal human interaction.

This technique also has the potential to scale up for qubits consisting of more than one phosphorus atoms, where the number of possible image configurations would exponentially increase. However, machine learning-based framework could readily include any number of possible configurations.

In the coming years, as the number of qubits increase and size of quantum devices grow, qubit characterisation via manual measurements is likely to be highly challenging and onerous.

This work shows how machine learning techniques such as developed in this work could play a crucial role in this aspect of the realisation of a full-scale fault-tolerant universal quantum computer – the ultimate goal of the global research effort.

Banner: A map of electron wave function patterns, where the symmetry, brightness and size of features is directly related to the position of a phosphorus atom in silicon lattice. Picture: M.Usman/ University of Melbourne

This article was first published on Pursuit. Read the original article.

Source:  University of Melbourne.  Dr Muhammad Usman and Professor Lloyd Hollenberg,  Machine learning to scale up the quantum computer…

Content may have been edited for style and clarity.